-
Notifications
You must be signed in to change notification settings - Fork 962
/
Copy pathconvert_mot17_to_coco.py
133 lines (124 loc) · 6.6 KB
/
convert_mot17_to_coco.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
import os
import numpy as np
import json
import cv2
# Use the same script for MOT16
DATA_PATH = 'datasets/mot'
OUT_PATH = os.path.join(DATA_PATH, 'annotations')
SPLITS = ['train_half', 'val_half', 'train', 'test'] # --> split training data to train_half and val_half.
HALF_VIDEO = True
CREATE_SPLITTED_ANN = True
CREATE_SPLITTED_DET = True
if __name__ == '__main__':
if not os.path.exists(OUT_PATH):
os.makedirs(OUT_PATH)
for split in SPLITS:
if split == "test":
data_path = os.path.join(DATA_PATH, 'test')
else:
data_path = os.path.join(DATA_PATH, 'train')
out_path = os.path.join(OUT_PATH, '{}.json'.format(split))
out = {'images': [], 'annotations': [], 'videos': [],
'categories': [{'id': 1, 'name': 'pedestrian'}]}
seqs = os.listdir(data_path)
image_cnt = 0
ann_cnt = 0
video_cnt = 0
tid_curr = 0
tid_last = -1
for seq in sorted(seqs):
if '.DS_Store' in seq:
continue
if 'mot' in DATA_PATH and (split != 'test' and not ('FRCNN' in seq)):
continue
video_cnt += 1 # video sequence number.
out['videos'].append({'id': video_cnt, 'file_name': seq})
seq_path = os.path.join(data_path, seq)
img_path = os.path.join(seq_path, 'img1')
ann_path = os.path.join(seq_path, 'gt/gt.txt')
images = os.listdir(img_path)
num_images = len([image for image in images if 'jpg' in image]) # half and half
if HALF_VIDEO and ('half' in split):
image_range = [0, num_images // 2] if 'train' in split else \
[num_images // 2 + 1, num_images - 1]
else:
image_range = [0, num_images - 1]
for i in range(num_images):
if i < image_range[0] or i > image_range[1]:
continue
img = cv2.imread(os.path.join(data_path, '{}/img1/{:06d}.jpg'.format(seq, i + 1)))
height, width = img.shape[:2]
image_info = {'file_name': '{}/img1/{:06d}.jpg'.format(seq, i + 1), # image name.
'id': image_cnt + i + 1, # image number in the entire training set.
'frame_id': i + 1 - image_range[0], # image number in the video sequence, starting from 1.
'prev_image_id': image_cnt + i if i > 0 else -1, # image number in the entire training set.
'next_image_id': image_cnt + i + 2 if i < num_images - 1 else -1,
'video_id': video_cnt,
'height': height, 'width': width}
out['images'].append(image_info)
print('{}: {} images'.format(seq, num_images))
if split != 'test':
det_path = os.path.join(seq_path, 'det/det.txt')
anns = np.loadtxt(ann_path, dtype=np.float32, delimiter=',')
dets = np.loadtxt(det_path, dtype=np.float32, delimiter=',')
if CREATE_SPLITTED_ANN and ('half' in split):
anns_out = np.array([anns[i] for i in range(anns.shape[0])
if int(anns[i][0]) - 1 >= image_range[0] and
int(anns[i][0]) - 1 <= image_range[1]], np.float32)
anns_out[:, 0] -= image_range[0]
gt_out = os.path.join(seq_path, 'gt/gt_{}.txt'.format(split))
fout = open(gt_out, 'w')
for o in anns_out:
fout.write('{:d},{:d},{:d},{:d},{:d},{:d},{:d},{:d},{:.6f}\n'.format(
int(o[0]), int(o[1]), int(o[2]), int(o[3]), int(o[4]), int(o[5]),
int(o[6]), int(o[7]), o[8]))
fout.close()
if CREATE_SPLITTED_DET and ('half' in split):
dets_out = np.array([dets[i] for i in range(dets.shape[0])
if int(dets[i][0]) - 1 >= image_range[0] and
int(dets[i][0]) - 1 <= image_range[1]], np.float32)
dets_out[:, 0] -= image_range[0]
det_out = os.path.join(seq_path, 'det/det_{}.txt'.format(split))
dout = open(det_out, 'w')
for o in dets_out:
dout.write('{:d},{:d},{:.1f},{:.1f},{:.1f},{:.1f},{:.6f}\n'.format(
int(o[0]), int(o[1]), float(o[2]), float(o[3]), float(o[4]), float(o[5]),
float(o[6])))
dout.close()
print('{} ann images'.format(int(anns[:, 0].max())))
for i in range(anns.shape[0]):
frame_id = int(anns[i][0])
if frame_id - 1 < image_range[0] or frame_id - 1 > image_range[1]:
continue
track_id = int(anns[i][1])
cat_id = int(anns[i][7])
ann_cnt += 1
if not ('15' in DATA_PATH):
#if not (float(anns[i][8]) >= 0.25): # visibility.
#continue
if not (int(anns[i][6]) == 1): # whether ignore.
continue
if int(anns[i][7]) in [3, 4, 5, 6, 9, 10, 11]: # Non-person
continue
if int(anns[i][7]) in [2, 7, 8, 12]: # Ignored person
category_id = -1
else:
category_id = 1 # pedestrian(non-static)
if not track_id == tid_last:
tid_curr += 1
tid_last = track_id
else:
category_id = 1
ann = {'id': ann_cnt,
'category_id': category_id,
'image_id': image_cnt + frame_id,
'track_id': tid_curr,
'bbox': anns[i][2:6].tolist(),
'conf': float(anns[i][6]),
'iscrowd': 0,
'area': float(anns[i][4] * anns[i][5])}
out['annotations'].append(ann)
image_cnt += num_images
print(tid_curr, tid_last)
print('loaded {} for {} images and {} samples'.format(split, len(out['images']), len(out['annotations'])))
json.dump(out, open(out_path, 'w'))